Re: [PATCH 0/2] Update CascadelakeX and SkylakeX events list

From: Jin, Yao
Date: Thu Sep 17 2020 - 22:23:33 EST

Hi Ian,

On 9/18/2020 9:36 AM, Ian Rogers wrote:
On Thu, Sep 17, 2020, 6:21 PM Jin, Yao <yao.jin@xxxxxxxxxxxxxxx> wrote:

Hi Arnaldo,

On 9/7/2020 4:01 PM, Jin, Yao wrote:
Hi Arnaldo,

On 7/17/2020 2:06 PM, Jin, Yao wrote:

On 6/17/2020 3:38 AM, Arnaldo Carvalho de Melo wrote:
Em Tue, Jun 16, 2020 at 02:27:40PM +0800, Jin, Yao escreveu:
On 6/16/2020 2:16 PM, Ian Rogers wrote:
On Mon, Jun 15, 2020 at 6:00 PM Jin, Yao <yao.jin@xxxxxxxxxxxxxxx>
Can I get an ACK for this patchset?
On 6/3/2020 10:18 AM, Jin Yao wrote:
This patchset updates CascadelakeX events to v1.08 and
updates SkylakeX events to v1.21.

The events have been tested on CascadelakeX and SkylakeX
servers with latest perf/core branch.

could you rebase this on Arnaldo's tmp.perf/core tree?
I tried using git am but get:
Applying: perf vendor events: Update CascadelakeX events to v1.08
error: patch fragment without header at line 279: @@ -213,14 +220,14
error: could not build fake ancestor
Patch failed at 0001 perf vendor events: Update CascadelakeX events
to v1.08


The patchset are applied OK on perf/core branch.

As far as I understand, the patch for posting should be based on
perf/core branch, is it right?

Sorry, I've been testing with using tmp.perf/core as a way to more
quickly make available what I've processed, before I test it thoroughly
both with container builds and with manual testing, so the bleeding
is there, perf/core becoming a bit more stable, as I'll try not to
rebase it like before.

- Arnaldo

Can this event update be accepted?

Jin Yao

Can this event list update be accepted?

Jin Yao

Ping again. :)

Can this event update patchset be accepted?

@Ian, I remembered you had tried this patchset and it's OK right?

The previous patch didn't apply cleanly. I tested what I had and it solved
a problem with metrics derived from recent the most recent tma metrics -
which is great! I will retest with the latest patch.

This patchset can be applied on perf/core. I double checked with the latest perf/core branch.

Did you have a chance to look at the skylake parallel reads metric? The arb
thresh modifier isn't present. There are issues with other metrics where
the units are scaled twice. Have these been resolved?

I will look at the SKL/KBL desktop metric issues. If it needs, I will post another patchset for desktop event update.

Jin Yao


Jin Yao